Our own product · Built in-house
An instrument, not an opinion.
A scoring engine, a published newspaper, and a fix plan, designed and built as one product.
The Answer Report is our own product. It measures how well an AI assistant can read a business website, publishes the score, and hands over the fix.
People increasingly ask an assistant who to hire before they ever open a search box, and most websites give those systems almost nothing to work with. There was no honest instrument for that, only opinions and vendors selling a feeling. So we built one. A deterministic engine that scores a site out of 100 across the things an assistant actually reads, an editorial layer that publishes those scores as a newspaper with one city edition at a time, and the rails that keep the whole thing running with nobody standing next to it.
Specs
Product design, Engine, Editorial design, Automation
Measure, publish, fix, re-check
Small business, EN
2026, live
Context
The Challenge
A product that grades other people has to be unarguable, so almost every design decision here is really a decision about trust.
A number nobody can argue with.
A score is worthless if two runs disagree. Every check is deterministic, the pages sampled are chosen by a fixed rule, and each result quotes the exact page text behind it. Nothing is estimated and nothing is invented.
It has to pass its own test.
A product about being readable by machines cannot itself be unreadable by machines. It publishes its own score, produced by the same engine, and prints the honest number rather than a flattering one.
Strangers get to run it.
The audit is open to anyone, with no email and no account. That is an open door into a machine that costs real money to run, so the door had to be built properly.
Nobody is standing next to it.
Auditing, publishing, delivery and monitoring all had to run on their own schedule, on hardware that does not care whether a laptop is open.
Execution
The Solution
One product in three layers: the engine that measures, the publication that carries it, and the automation that runs both.
Roadmap
What it does now
Three city editions are published, the engine grades itself in public, and the findings have started doing the arguing.
Currently Optimizing
It publishes its own score
The engine gives this site 93 out of 100. The missing points are a phone number the publication does not have, and rather than invent one to round the number up, the correction is printed on the front page.
The findings are part of the product
Across three cities, 153 of the 173 businesses probed were named by neither assistant, while a pair of national directories out-named every real business in the set. That is published, with the method, for anyone to check.
One insight worth the whole build
A default setting on a very common hosting layer quietly blocks AI crawlers and hides the contact address behind obfuscation. Turning it off is what took our own studio site from 60 to 93. Most owners have no idea it is on.
The Backlog
A city at a time
Adding an edition is a data step rather than a development one, so the publication grows by cities instead of by releases.
"We wanted an instrument, not an opinion. If a score is going to cost someone money to fix, it has to come out the same every time and it has to show its evidence."
Vonzie Studio